Scientific Publications

The DCR, a self-administered, automatically scored digital test of cognition, can also classify informant-based clinically relevant levels of functional impairment in older adults in around 3-5 minutes. The high negative predictive value emphasizes the utility of the DCR to dispel concerns of impairment of iADLs/ADLs or dementia. We found strong links between DCR and FAQ, which resulted in the robust ability of the DCR to determine individuals who are unlikely to be functionally impaired. This can help primary-care providers streamline the clinical decision-making, triage, and intervention planning along the spectrum of MCI and early dementia.

Our findings demonstrate the added utility of the DCR, an automated, process-driven, and process-based digital cognitive assessment when compared to the Mini-Cog, a commonly used tool that relies on fixed clock scoring rules. We additionally demonstrated variability in manually scoring the Mini-Cog, even among experts. Digital process-based metrics capture dynamic processes in clock drawing and perform better in detecting cognitive impairment in a diagnosed research cohort of older individuals.

The digital speech hearing screener (dSHS) successfully differentiates between hearing impaired and unimpaired individuals in under 3 minutes. This hearing screener offers a time saving, in clinic hearing screening to streamline the triage of those with likely hearing impairment to the appropriate follow up assessment, thereby improving the quality of services. Additionally, this tool can help to rule out hearing impairment as a cause or confounder of cognitive impairment.

We discuss the current advances and future directions in capturing individualized brain health outcomes and present an approach to integrate person-centered outcome in a scalable manner. Our approach stems from the evidence-based electronic Person-Specific Outcome Measure (ePSOM) program which prompts an individual to define personally meaningful treatment priorities and report level of confidence in managing items that matter to the individual the most.

Digital assessment technology elegantly quantifies occult, nuanced behavior not previously appreciated, operationally defines critical underlying neurocognitive constructs related to functional abilities, and yields selected process-based scores that outperform traditional paper/pencil test scores for participant classification. When brought to scale, the Linus Health dTMT-B test could be a sensitive tool to detect subtle-to-mild functional deficits in emergent neurodegenerative illnesses.

This research demonstrates the DCTclock’s ability to estimate the 5-year risk of developing dementia in an African American population. Early detection of elevated dementia risk using the DCTclock could provide patients, caregivers, and clinicians opportunities to plan and intervene early to improve cognitive health trajectories. Early detection of dementia risk can also enhance participant selection in clinical trials while reducing screening costs.

Multimodal models incorporating graphomotor, memory, and speech and voice features provided the stronger classification performance. Multimodal models were superior to all other single modality and demographics models. The current research contributes to the prevailing multimodal profile of those with cognitive impairment, suggesting that it is associated with slower speech with a particular effect on the duration, frequency, and percentage of pauses compared to normal healthy speech.

Our results demonstrated that a subject-specific prognostic model for speech predicts future articulatory precision and ALSFRS-R speech values accurately.

Screening in primary care using the DCR is feasible, takes less time to administer than MoCA or SLUMS, and shows concordant results with these more established screening tools in detecting cognitive impairment. Future research aims to investigate the criterion validity of the DCR among biomarkers for neurodegenerative disease.

Our results demonstrated that a subject-specific prognostic model for speech predicts future articulatory precision and ALSFRS-R speech values accurately.

The CCE is a powerful neurocognitive assessment tool that is sensitive to patient’s subjective concerns about possible decline in memory, mood symptoms, possible cognitive impairment, and cardiovascular risk. iPad administration ensures total reliability for test administration and scoring. The CCE is easily deployable in outpatient ambulatory primary care settings.

A study of 248 community dwelling older adults found that a balance test instrumented within inertial sensors could accurately and reliably estimate the risk of falls.

Findings from a study in 168 community dwelling older adults showed that The Five Times Sit to Stand (FTSS) test and wearable sensors can provide accurate estimation of falls risk, balance impairment and cognitive decline

The results show that reported accuracy declines as a function of increasing sample size, with small sample size studies yielding an overoptimistic estimate of the accuracy. For correctly trained models, this is unexpected as the ability of a machine learning model to predict group membership ought to remain the same or improve with additional training data. We posit that the overoptimism is the result of a combination of publication bias and overfitting and suggest mitigation strategies.

The fully automated measure was accurate (r = .84), had moderate to good reliability (intra-class correlation = .73), correlated with MiniMental State Examination and improved the fit in the context of other automatic language features (r = .65), and longitudinally declined with age and level of cognitive impairment. This study demonstrates the use of a rigorous analytical and clinical framework for validating automatic measures of speech, and applied it to a measure that is accurate and clinically relevant.

Significant differences in cepstral peak prominence, degree of voice breaks, jitter, vowel space area, pitch, and vowel space area were observed after Opus processing, providing insight into the types of acoustic measures that are susceptible to speech compression algorithms.

Our results reflect slower PFC activation in participants with PD which correlates with behavioral measures. In addition, the findings of the study indicate the importance of performing the CDT copy task condition that detect early cognitive decline in participants with PD.

This study shows that a very small number of latent variables are sufficient to encode important clock drawing anomalies that are predictive of dementia.

The results show that reported accuracy declines as a function of increasing sample size, with small sample size studies yielding an overoptimistic estimate of the accuracy. For correctly trained models, this is unexpected as the ability of a machine learning model to predict group membership ought to remain the same or improve with additional training data. We posit that the overoptimism is the result of a combination of publication bias and overfitting and suggest mitigation strategies.

The fully automated measure was accurate (r = .84), had moderate to good reliability (intra-class correlation = .73), correlated with MiniMental State Examination and improved the fit in the context of other automatic language features (r = .65), and longitudinally declined with age and level of cognitive impairment. This study demonstrates the use of a rigorous analytical and clinical framework for validating automatic measures of speech, and applied it to a measure that is accurate and clinically relevant.

Significant differences in cepstral peak prominence, degree of voice breaks, jitter, vowel space area, pitch, and vowel space area were observed after Opus processing, providing insight into the types of acoustic measures that are susceptible to speech compression algorithms.

Our results reflect slower PFC activation in participants with PD which correlates with behavioral measures. In addition, the findings of the study indicate the importance of performing the CDT copy task condition that detect early cognitive decline in participants with PD.

A study of 248 community dwelling older adults found that a balance test instrumented within inertial sensors could accurately and reliably estimate the risk of falls.

Findings from a study in 168 community dwelling older adults showed that The Five Times Sit to Stand (FTSS) test and wearable sensors can provide accurate estimation of falls risk, balance impairment and cognitive decline.

This study shows that a very small number of latent variables are sufficient to encode important clock drawing anomalies that are predictive of dementia.

Command digit misplacement is negatively associated with semantics, visuospatial, visuoconstructional, and reasoning and negatively associated with connectivity from the basal nucleus of Meynert (BNM) to the anterior cingulate cortex (ACC). Individuals with MCI had more misplacement and less BNM-ACC connectivity. Total completion time involved posterior and cerebellar associations only. Findings suggest clock drawing digit placement accuracy may be a unique metric of mental planning and provide insight into neurodegenerative disease.

dCDT composite scores were significantly associated with multiple brain MRI measures in a large community-based cohort. The dCDT has the potential to be used as a cognitive assessment tool in the clinical diagnosis of MCI.

These results suggest that DCTclock command/copy parameters can dissociate CN, SbCI, and MCI subtypes. The larger effect sizes for command clock indices suggest these metrics are sensitive in detecting early cognitive decline. Additional research with a larger sample is warranted.

A study of 115 community dwelling older adults completing three trials of a 30-metre walk task, evaluated the reliability of spatiotemporal gait parameters, their variability, and asymmetry, calculated from body-worn bilateral inertial sensor data using Gait™ and showed that quantified gait measures can be obtained from three gait cycles of bilateral data.

A real-world study of the Kinesis Balance application with 594 smartphone assessments from 147 unique phones found a strong association between self-reported falls history and balance impairment scores, suggesting that it may be a clinically useful tool for assessing balance and falls risk. This has utility in a variety of settings, including remote monitoring platform for remote functional assessment or as part of decentralised clinical trials.

QTUG™ has been successfully used to measure change in physical function and the response to intervention in both community dwelling older adults.

A study of 1057 participants, including 71 previously diagnosed with Parkinson’s Disease (PD)18, found that QTUG data can predict fall counts in PD and that falls counts predicted from the inertial sensor data obtained during a simple walking task have the potential to be developed as a novel digital biomarker for PD.

We found that the predicted and observed FVC values in the test sample had a correlation coefficient of .80 and mean absolute error between .54 L and .58 L (18.5% to 19.5%). In addition, we found that the model was able to detect longitudinal decline in FVC in the test sample, although to a lesser extent than the observed FVC values measured using a spirometer, and was highly repeatable (ICC = 0.92–0.94), although to a lesser extent than the actual FVC (ICC = .97). These results suggest that sustained phonation may be a useful surrogate for VC in both research and clinical environments.

SemR is reliable, shows convergent validity with MMSE, and correlates strongly with manual hand-counts. SemR declines with age and severity of cognitive impairment, with the speed of decline differing by level of impairment.

Digital variables from clock copy condition provided predictive value over common demographic and comorbidity variables. We hypothesize this is due to the sensitivity of the copy condition to executive dysfunction, as has been shown in previous studies for subtypes of cognitive impairment. Individuals undergoing TAVR procedures are often frail and executively compromised due to their cerebrovascular disease. We encourage additional research on the value of digitally-acquired clock drawing within different surgery types. Type of cognitive impairment and the value of digitally-acquired CDT command and copy parameters in other surgeries remain unknown.

Adults age 55 plus produce symmetric clock faces with one stroke, with minimal overshoot and digit misplacement, and hands with expected hour hand to minute hand ratio. Data suggest digitally acquired graphomotor and latency differences based on handedness, age, education, and anchoring.

Conclusion: Data provide useful benchmarks from which to assess digital clock drawing performance in Alzheimer’s disease and related dementias.

By extracting dCDT features, cognitive impairment and AD patients can be identified early. Through dCDT feature extraction, a prediction model of single cognitive domain damage can be established.

The performances of the digital and paper-and-pencil pentagon drawing tests were comparable in the screening of dementia. The digital CDT demonstrated better diagnostic performance than paper-and-pencil CDT for MCI. Other types of digital drawing tests showed comparable performance with paper-and-pencil formats. Therefore, digital drawing tests can be used as an alternative tool for the screening of MCI and dementia.

DCTclock discriminates between diagnostic groups and improves upon traditional cognitive tests for detecting biomarkers of amyloid and tau pathology in CN older adults. The validation of such digitized measures has the potential of providing an efficient tool for detecting early cognitive changes along the AD trajectory.

We benchmarked DCTclock against existing clock scoring systems and the Mini-Mental Status Examination, a widely-used but lengthier cognitive test, and showed that DCTclock offered a significant improvement in the detection of early cognitive impairment and the ability to characterize individuals along the Alzheimer's disease trajectory. This offers an example of a robust framework for creating digital biomarkers that can be used clinically and in research for assessing neurological function.

The dCDT can potentially be used as a tool for cognitive assessment in large community-based populations.

The use of quantitative digital cognitive assessment showed greater sensitivity in identifying subtle cognitive decline than the current standardized tests. Differences in cognitive profiles were observed based on genotype. The identification of early cognitive decline may improve the clinical management of PD patients and be useful for cognitive related clinical trials.

The dCDT is able to operationally define graphomotor output that cannot be measured using traditional paper and pencil test administration in older health controls and participants with dementia. These data suggest that kinematic, time-based, and visuospatial behavior obtained using the dCDT may provide additional neurocognitive biomarkers that may be able to identify and tract dementia syndromes.

Digitally-acquired clock drawing profiles differ between PD and non-PD peers, and distinguish PD cognitive phenotypes.

To model the ost-effectiveness of QTUG, Independent publication by Sheffield Teaching Hospital (STH) NHS Foundation Trust, ScHARR (University of Sheffield) and Kinesis Health Technologies Ltd

A study in 37 patients with Multiple Sclerosis (MS) found that short bouts of gait data, from a limited number of gait cycles, collected using Kinesis Gait™, can provide reliable gait measurements for people with MS. Stride time variability and asymmetry, as well as stride velocity variability and asymmetry, were identified as potential digital biomarkers for gait assessments in people with MS. Kinesis Gait™ be used to objectively assess gait in people with MS, even with fragmented data. This could have important implications for the monitoring of symptoms and the development of new treatments for MS

Bulbar deterioration in amyotrophic lateral sclerosis (ALS) is a devastating characteristic that impairs patients’ ability to communicate, and is linked to shorter survival. The existing clinical instruments for assessing bulbar function lack sensitivity to early changes. In this paper, using a cohort of N = 65 ALS patients who provided regular speech samples for 3–9 months, we demonstrated that it is possible to remotely detect early speech changes and track speech progression in ALS via automated algorithmic assessment of speech collected digitally.

Our results demonstrate that the repeatability of speech features extracted using open-source tool kits is low. Researchers should exercise caution when developing digital health models with open-source speech features. We provide a detailed summary of feature-by-feature repeatability results (ICC, WSCV, SE of measurement, limits of agreement for WSCV, and minimal detectable change) in the online supplementary material so that researchers may incorporate repeatability information into the models they develop.

The digital clock drawing test is feasible to administer and is highly acceptable to older adults in a preoperative setting. We demonstrated a significant association between both the dCDT time and clock score metrics, with the established 4AT. Our results provide convergent validity of the dCDT in the preoperative setting.

Early identification of emergent neurodegenerative illness is criterial for better disease management. Applying machine learning to standard neuropsychological tests promises to be an effective first line screening method for classification of non-MCI and MCI subtypes.

Command dCDT variables of interest were primarily processing speed and working memory dependent. MCI participants showed dCDT differences relative to non-MCI peers, suggesting the dCDT may assist with classification. Results document cognitive construct validation to digital metrics of clock drawing.

A study of 8,521 participants assessed using Kinesis QTUG™, examined gait, mobility and falls risk in 38 organizations in 6 countries over a 5 year period. We found that more than one fifth of older adults who have never reported a fall were at high risk and would perhaps stand to benefit most from an intervention. Similarly, by comparing against a large reference data set, some form of gait impairment was noted in almost 1 out of 5 of participants. One in four patients were predicted to be at high risk of falls with a similar proportion reporting a fall in the past 12 months.

Clock drawing construction slowed for nearly one-quarter of patients after total knee atrthroplasty (TKA) surgery, whereas nonsurgery peers showed the expected practice effect, ie, speed increased from baseline to follow-up time points. Future research should investigate the neurobiological basis for these changes after TKA.

Mobility parameters derived using Kinesis QTUG™ and Gait™ have been shown to provide reliable measurement of gait and mobility and have utility in predicting falls in patients with Parkinson’s disease (PD)

In community-dwelling older adults (N=37), these preliminary results show that a cognitive dual-task significantly (P < 0.025) affects QTUG performance in almost all parameters, with a significant (P < 0.025) reduction in time-to-stand observed with a motor task

Longer age-related decision making latencies may reflect a greater need for working memory and increased self-monitoring in older subjects. These latency measures have potential to serve as neurocognitive biomarkers of Alzheimer's disease and other insidious neurodegenerative disorders.

Mobility parameters derived using Kinesis QTUG™ and Gait™ have been shown to provide reliable measurement of gait and mobility in: patients with multiple sclerosis (MS)

QTUG™ has been validated both prospectively (N=226) and cross-sectionally (N=748), and has been shown to provide an accurate measure of falls risk in older adults

An easily observable graphomotor distinction was associated with 1) better performance in specific cognitive domains, 2) higher local efficiency suggesting better regional integration, and 3) more sophisticated modular integration involving the ventral ('what') visuospatial processing stream. Taken together, these results enhance our knowledge of the brain-behavior relationships underlying unprompted graphomotor organization during dCDT.

Mobility parameters derived using Kinesis QTUG™ and Gait™ have been shown to provide reliable measurement of gait and mobility in: patients with multiple sclerosis (MS).

We worked with clinicians to define guidelines for model interpretability, and constructed sparse linear models and rule lists designed to be as easy to use as scoring systems currently used by clinicians, but more accurate. While our models will require additional testing for validation, they offer the possibility of substantial improvement in detecting cognitive impairment earlier than currently possible, a development with considerable potential impact in practice.

A study of 119 older adults showed that changes in QTUG parameters were strongly associated with decline in balance as measured using the Berg Balance Scale (BBS)

The study suggests that the combination of three physical assessments (timed up and go (TUG), five times sit to stand (FTSS) and quiet standing balance), quantified using body-worn inertial sensors, could lead to improved methods for assessing frailty and falls risk in older adults.

The study suggests that inertial sensor parameters derived using QTUG in patients with MS were reliable and could be used to predict disease severity as measured by the EDSS and MSIS scale.

QTUG™ has been validated both prospectively (N=226) and cross-sectionally (N=748), and has been shown to provide an accurate measure of falls risk in older adults.

The dCDT differentiated aspects of psychomotor slowing in depression regardless of age, while dCDT/cognitive associates for younger adults with depression mimicked patterns of older euthymics.

A study of 399 older adults showed that QTUG™ provides a robust and reliable estimate of patient’s frailty state as defined using the Fried frailty phenotype.

The five-times-sit-to-stand test (FTSS) is an established assessment of lower limb strength, balance dysfunction and falls risk. Quantifying the movement using tri-axial accelerometers may provide a more objective and potentially more accurate falls risk estimate.

The novel method of functional mobility assessment using QTUG provides a reliable means to quantify subtle changes in mobility during postural transitions in an exercise program.

This study highlights the potential of instrumented gait and balance assessments in distinguishing fallers from non-fallers among older adults. While single support time showed significant diurnal variation in its association with falls history, other gait and quiet standing balance parameters remained consistent throughout the day. These findings suggest that, aside from specific measures like single support time, the timing of assessments may not significantly impact their effectiveness in identifying fall risk.

The inertial sensor algorithms contained in Kinesis QTUG™ have been validated against gold standards (optical motion capture system, forceplate and GAITRite) for assessment of temporal and spatial gait parameters in normal and pathological gait as well as treadmill running.

The study looked at a number of standard quantitative balance parameters and the method based on estimating changes in the magnitude of pressure exerted on the sensor matrix was most promising, informing home-based balance measurement in future studies.

A longitudinal study of 189 older adults showed that the change in mobility parameters obtained using QTUG™ measured two years after baseline assessment are associated with cognitive decline in older adults.

The study compared the classification accuracy of the model with an established method for falls risk assessment, the Berg balance scale. The results of the study showed that the model was more accurate than the Berg balance scale in classifying falls history and assessing falls risk.

QTUG™ has been validated prospectively (N=226), and has been shown to provide an accurate measure of falls risk in older adults.

Mobility parameters derived using Kinesis QTUG™ have been shown to be strongly linked to Minimum Ground Clearance (MGC), which is strongly linked to risk of falls in older adults.

The inertial sensor algorithms contained in Kinesis QTUG™ have been validated against gold standards (optical motion capture system, forceplate and GAITRite) for assessment of temporal and spatial gait parameters in normal and pathological gait as well as treadmill running.

Mobility parameters derived using Kinesis QTUG™ have been shown to provide reliable measurement of gait and mobility, showcasing fair to good test-retest reliability.

Mobility parameters derived using Kinesis QTUG™ have been shown to be strongly linked to Minimum Ground Clearance (MGC)21, which is strongly linked to risk of falls in older adults.

The findings of the study of 349 community-dwelling elderly adults suggest the QTUG offers an improvement over two standard falls risk assessments (TUG and BBS) and has shown to provide an accurate measure of falls risk in older adults